2026-06-02T10:32:20Zhttps://www.radar-service.eu/oai/OAIHandler
10.35097/7xxzf81799hcec8s2026-03-03T14:22:35Zradar4kit
10.35097/7xxzf81799hcec8s Sielemann, Anne Anne Sielemann 0000-0002-9534-1259 Fraunhofer Institute of Optronics, System Technologies and Image Exploitation Wolf, Stefan Stefan Wolf Fraunhofer Institute of Optronics, System Technologies and Image Exploitation Roschani, Masoud Masoud Roschani Fraunhofer Institute of Optronics, System Technologies and Image Exploitation Beyerer, Jürgen Jürgen Beyerer Fraunhofer Institute of Optronics, System Technologies and Image Exploitation Ziehn, Jens Jens Ziehn 0000-0001-9872-1903 Fraunhofer Institute of Optronics, System Technologies and Image Exploitation Synset Boulevard Fraunhofer Institute of Optronics, System Technologies and Image Exploitation,Karlsruhe Institute of Technology,Vollat, Matthias,Ruf, Miriam 2024 2026 Computer Science KAMO VMMR machine learning vehicle make and model recognition Open Access Creative Commons Attribution 4.0 International Fraunhofer Institute of Optronics, System Technologies and Image Exploitation https://ror.org/01zx97922 The Synset Boulevard dataset is designed for the task of vehicle make and model recognition (VMMR), and is—to the best of our knowledge—the first entirely synthetically generated large-scale VMMR image dataset. Through the simulation of image data rather than the manual annotation of real data, it is intended to mitigate common challenges in state-of-the-art VMMR datasets, namely bias, human error, privacy, and the challenge of providing systematic updates. On the other hand, the provision and use of synthetic data introduce individual challenges, such as potential domain gaps and a less pronounced intra-class variance. The dataset was generated using path tracing and physically-based, data-driven models, and contains 32,400 independent images (each with different imaging simulations and with/without masked license plates, leading to a total of 259,200 images) from 162 different vehicle models of 43 makes depicted in front view. It is split into 8 sub-datasets to investigate the influence of optical/imaging effects on the classification ability. en Mobilithek GERMANY Ministerium für Wirtschaft, Arbeit und Wohnungsbau Baden-Württemberg https://ror.org/04sed8n13 FeinSyn Fraunhofer Society https://ror.org/05hkkdn48 PREPARE 40-02702 ML4Safety 6,7 GB application/x-tar